Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced CaRL (Capability-aligned Reinforcement Learning), a method that trains large language models to refuse futile reasoning on tasks beyond their capability, reducing computationally expensive yet sema…
Kireo built a low-latency semantic memory layer for coding agents using LanceDB and a CPU-hosted embedding model, enabling on-demand retrieval via MCP tools. The system combines vector and keyword search with RRF fusion …
Kakao detailed improvements to its Kanana-o speech model on August 4, 2026, enabling users to control speaking speed, volume, pitch, emotion, intonation, and dialect via natural-language prompts. In Kakao's Korean Instru…
Applied Compute added native on-policy self-distillation (OPSD) and relevance-masked self-distillation (RMSD) workflows to its AC2 platform, enabling enterprise AI teams to convert production traces and user corrections …
A developer has built Pulse, an AI debugger that visualizes tensors and gradients as live heatmaps and automatically pinpoints fixes for broken machine learning models. The tool runs during idle CPU time to avoid interfe…
Swiftlet, a 10,000-line Swift and Metal project under Apache 2.0, runs Alibaba's Qwen3-Next-80B-A3B at 4-bit in 4.3GB of peak RAM on a Mac, decoding at 4.5–5 tokens per second on an M5, and runs the Qwen3.6-35B-A3B on an…
Three independent benchmarks show that expensive AI defaults are rarely optimal: medium reasoning effort captures nearly all of Claude Opus 5's bug-fix gains, a three-model open-weight jury (GPT-OSS 120B, DeepSeek-V4 Fla…
A new study from arXiv (2608.00045v1) finds that textual descriptors alone can predict early-stage startup success, defined as Exit, without relying on contextual, financial, or human capital variables. Analyzing 7,419 s…
Researchers introduced Noise-Robust Conditional Flow Matching (NR-CFM), a generative model that learns clean data distributions directly from noisy measurements, achieving competitive performance with Ambient Diffusion i…
Researchers propose PhysAgent, an inference-time multi-agent framework that uses a lightweight 4B multimodal large language model, Qwen3-VL-4B, to verify candidate heart-rate estimates from multiple rPPG models, improvin…
Researchers from an unnamed institution tested hybrid quantum convolutional neural networks (QCNNs) with 2 and 4 qubits to classify volcanic clouds in SEVIRI satellite images, comparing their performance to classical arc…
A new unsupervised spatio-temporal stratification protocol reduces maximum cross-subset intensity bias from 34.1% to under 2.1% in longitudinal brain MRI cohorts, according to a study on arXiv (2608.00073v1). The Tripart…
Researchers propose LeapTalk, a framework for real-time talking-head generation that achieves high-fidelity video synthesis in a single forward step at up to 200 FPS, addressing the latency-quality trade-off in existing …
Researchers propose a ControlNet-based diffusion framework for map-to-satellite image synthesis that conditions on OpenStreetMap raster maps and their stationary wavelet transform (SWT) subbands, using two adapters fused…
Researchers introduced PRISMS, a closed-loop framework that detects and steers tool-use failures in agentic LLMs using sparse MLP neuron readouts, achieving ROC-AUC 0.90-1.00 for over-calling and missing detection and 0.…
Researchers propose AdaMTP, an adaptive training paradigm for multi-token prediction that dynamically aligns prediction horizons with sequence predictability, outperforming standard MTP across mathematical reasoning, cod…
Researchers introduced an executable benchmark and a budget-aware meta-router for agentic workflows, achieving 100% success on held-out test tasks versus 93.5% for static workflows, with 43% lower cost. The benchmark inc…
Researchers propose a multiplicative policy shaping framework to steer pretrained deep reinforcement learning policies toward welfare-based fairness objectives at inference time without updating base policy parameters. T…
Researchers introduced a permutation-equivariant neural operator for collision-aware trajectory planning of spacecraft swarms, trained on ten spacecraft and generalizing zero-shot to swarms of 1,000 amid more than 11,000…
Researchers introduced ELECTRIC (Evidential Learning-Enhanced CT Reconstruction via Iterative Correction), a physics-guided Bayesian method that uses an evidential neural network to iteratively reconstruct CT images. In …